| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": null, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 40960, |
| "max_window_layers": 28, |
| "model_type": "qwen3", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "pad_token_id": 151643, |
| "problem_type": "regression", |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 1000000, |
| "rope_type": "default" |
| }, |
| "salience_document_payload_format": "Document:\\n[indexed source sentences]\\n\\nCandidate sentence:\\n[Sxxx] sentence", |
| "salience_instruction": "Given an indexed document and a designated candidate sentence, judge whether the candidate sentence contains information that is important for representing the document as a whole.", |
| "salience_loss_type": "mse", |
| "salience_query": "Is the designated candidate sentence salient to the document as a whole?", |
| "salience_reranker_bias": 0.49982699751853943, |
| "salience_reranker_false_token_id": 2152, |
| "salience_reranker_scale": 0.09945447742938995, |
| "salience_reranker_true_token_id": 9693, |
| "salience_score_aggregation": "scalar", |
| "salience_score_semantics": "model_balanced_salience_probability", |
| "salience_score_transform": "affine_yes_no_logit_difference", |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.6.2", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151669 |
| } |
|
|
